Sports Analytics algorithms for performance prediction

Sports Analytics is an emerging research area with several applications in a variety of fields. These could be, for example, the prediction of an athlete's or a team's performance, the estimation of an athlete's talent and market value, as well as the prediction of a possible injury. Teams and coaches are increasingly willing to embed such “tools” in their training, in order to improve their tactics. This paper reviews the literature on Sports Analytics and proposes a new approach for prediction. We conducted experiments using suitable algorithms mainly on football related data, in order to predict a player's position in the field. We also accumulated data from past years, to estimate a player's goal scoring performance in the next season, as well as the number of a player's shots during each match, known to be correlated with goal scoring probability. Results are very promising, showcasing high accuracy, particularly as the predicted number of goals was very close to the actual one.

I. Introduction

Sports analytics exist as a concept for many years, but a lot of steps are required in order to understand and improve team performance. It is a topic that is increasingly gaining interest recently [1], [2]. More and more teams try to use such solutions to improve performance. For the purposes of this paper we will mostly focus on football (soccer). We aim at predicting performance of individual players, based on previous seasons’ data. We tried to predict results in three major fields. In these experiments, a player’s position in the field could be predicted using suitable algorithms. By accumulating data from past years, we could have an estimation for a player’s goal scoring performance in the next season.